© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11966
    Prev
    Next
    INDEX
    Explanations

    backup and specific conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     społ
    0.52
     Oleg
    0.49
     egip
    0.48
    碚
    0.47
     पारिवार
    0.46
     محبوب
    0.46
     Hassan
    0.45
     Mirza
    0.44
     участка
    0.44
     pendekatan
    0.44
    POSITIVE LOGITS
     and
    0.62
    and
    0.57
    PL
    0.55
    is
    0.54
    '
    0.51
    MEs
    0.50
    ão
    0.47
    at
    0.46
     nerve
    0.46
    ம்
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.